Chromatin accessibility landscape of relapsed pediatric B-lineage acute lymphoblastic leukemia.

For around half of the pediatric B-lineage acute lymphoblastic leukemia (B-ALL) patients, the molecular mechanism of relapse remains unclear. To fill this gap in knowledge, here we characterize the chromatin accessibility landscape in pediatric relapsed B-ALL. We observe rewired accessible chromatin regions (ACRs) associated with transcription dysregulation in leukemia cells as compared with normal B-cell progenitors. We show that over a quarter of the ACRs in B-ALL are in quiescent regions with high heterogeneity among B-ALLs. We identify subtype-specific and allele-imbalanced chromatin accessibility by integrating multi-omics data. By characterizing the differential ACRs between diagnosis and relapse in B-ALL, we identify alterations in chromatin accessibility during drug treatment. Further analysis of ACRs associated with relapse free survival leads to the identification of a subgroup of B-ALL which show early relapse. These data provide an advanced and integrative portrait of the importance of chromatin accessibility alterations in tumorigenesis and drug responses.

Unbiased curriculum learning enhanced global-local graph neural network for protein thermodynamic stability prediction.

MOTIVATION: Proteins play crucial roles in biological processes, with their functions being closely tied to thermodynamic stability. However, measuring stability changes upon point mutations of amino acid residues using physical methods can be time-consuming. In recent years, several computational methods for protein thermodynamic stability prediction (PTSP) based on deep learning have emerged. Nevertheless, these approaches either overlook the natural topology of protein structures or neglect the inherent noisy samples resulting from theoretical calculation or experimental errors. RESULTS: We propose a novel Global-Local Graph Neural Network powered by Unbiased Curriculum Learning for the PTSP task. Our method first builds a Siamese graph neural network to extract protein features before and after mutation. Since the graph's topological changes stem from local node mutations, we design a local feature transformation module to make the model focus on the mutated site. To address model bias caused by noisy samples, which represent unavoidable errors from physical experiments, we introduce an unbiased curriculum learning method. This approach effectively identifies and re-weights noisy samples during the training process. Extensive experiments demonstrate that our proposed method outperforms advanced protein stability prediction methods, and surpasses state-of-the-art learning methods for regression prediction tasks. AVAILABILITY AND IMPLEMENTATION: All code and data is available at https://github.com/haifangong/UCL-GLGNN.

A denoised multi-omics integration framework for cancer subtype classification and survival prediction.

The availability of high-throughput sequencing data creates opportunities to comprehensively understand human diseases as well as challenges to train machine learning models using such high dimensions of data. Here, we propose a denoised multi-omics integration framework, which contains a distribution-based feature denoising algorithm, Feature Selection with Distribution (FSD), for dimension reduction and a multi-omics integration framework, Attention Multi-Omics Integration (AttentionMOI) to predict cancer prognosis and identify cancer subtypes. We demonstrated that FSD improved model performance either using single omic data or multi-omics data in 15 The Cancer Genome Atlas Program (TCGA) cancers for survival prediction and kidney cancer subtype identification. And our integration framework AttentionMOI outperformed machine learning models and current multi-omics integration algorithms with high dimensions of features. Furthermore, FSD identified features that were associated to cancer prognosis and could be considered as biomarkers.

Machine learning for the prediction of atherosclerotic cardiovascular disease during 3-year follow up in Chinese type 2 diabetes mellitus patients.

AIMS/INTRODUCTION: Clinical guidelines for the management of individuals with type 2 diabetes mellitus endorse the systematic assessment of atherosclerotic cardiovascular disease risk for early interventions. In this study, we aimed to develop machine learning models to predict 3-year atherosclerotic cardiovascular disease risk in Chinese type 2 diabetes mellitus patients. MATERIALS AND METHODS: Clinical records of 4,722 individuals with type 2 diabetes mellitus admitted to 94 hospitals were used. The features included demographic information, disease histories, laboratory tests and physical examinations. Logistic regression, support vector machine, gradient boosting decision tree, random forest and adaptive boosting were applied for model construction. The performance of these models was evaluated using the area under the receiver operating characteristic curve. Additionally, we applied SHapley Additive exPlanation values to explain the prediction model. RESULTS: All five models achieved good performance in both internal and external test sets (area under the receiver operating characteristic curve >0.8). Random forest showed the highest discrimination ability, with sensitivity and specificity being 0.838 and 0.814, respectively. The SHapley Additive exPlanation analyses showed that previous history of diabetic peripheral vascular disease, older populations and longer diabetes duration were the three most influential predictors. CONCLUSIONS: The prediction models offer opportunities to personalize treatment and maximize the benefits of these medical interventions.

Prediction of prognosis in COVID-19 patients using machine learning: A systematic review and meta-analysis.

BACKGROUND: Accurate prediction of prognostic outcomes in patients with COVID-19 could facilitate clinical decision-making and medical resource allocation. However, little is known about the ability of machine learning (ML) to predict prognosis in COVID-19 patients. OBJECTIVE: This study aimed to systematically examine the prognostic value of ML in patients with COVID-19. METHODS: A systematic search was conducted in PubMed, Web of Science, Embase, Cochrane Library, and IEEE Xplore up to December 15, 2021. Studies predicting the prognostic outcomes of COVID-19 patients using ML were eligible for inclusion. Risk of bias was evaluated by a tailored checklist based on Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Pooled sensitivity, specificity, and area under the receiver operating curve (AUC) were calculated to evaluate model performance. RESULTS: A total of 33 studies that described 35 models were eligible for inclusion, with 27 models presenting mortality, four intensive care unit (ICU) admission, and four use of ventilation. For predicting mortality, ML gave a pooled sensitivity of 0.86 (95% CI, 0.79-0.90), a specificity of 0.87 (95% CI, 0.80-0.92), and an AUC of 0.93 (95% CI, 0.90-0.95). For the prediction of ICU admission, ML had a sensitivity of 0.86 (95% CI, 0.78-0.92), a specificity of 0.81 (95% CI, 0.66-0.91), and an AUC of 0.91 (95% CI, 0.88-0.93). For the prediction of ventilation, ML had a sensitivity of 0.81 (95% CI, 0.68-0.90), a specificity of 0.78 (95% CI, 0.66-0.87), and an AUC of 0.87 (95% CI, 0.83-0.89). Meta-regression analyses indicated that algorithm, population, study design, and source of dataset influenced the pooled estimate. CONCLUSION: This meta-analysis demonstrated the satisfactory performance of ML in predicting prognostic outcomes in patients with COVID-19, suggesting the potential value of ML to support clinical decision-making. However, improvements to methodology and validation are still necessary before its application in routine clinical practice.

Predicting the efficacy of immune checkpoint inhibitors monotherapy in advanced non-small cell lung cancer: a machine learning method based on multidimensional data.

Immunotherapy has improved the prognosis of patients with advanced non-small cell lung cancer (NSCLC), but only a small subset of patients achieved clinical benefit. The purpose of our study was to integrate multidimensional data using a machine learning method to predict the therapeutic efficacy of immune checkpoint inhibitors (ICIs) monotherapy in patients with advanced NSCLC. We retrospectively enrolled 112 patients with stage IIIB-IV NSCLC receiving ICIs monotherapy. The random forest (RF) algorithm was used to establish efficacy prediction models based on five different input datasets, including precontrast computed tomography (CT) radiomic data, postcontrast CT radiomic data, a combination of the two CT radiomic data, clinical data, and a combination of radiomic and clinical data. The 5-fold cross-validation was used to train and test the random forest classifier. The performance of the models was assessed according to the area under the curve (AUC) in the receiver operating characteristic curve. Survival analysis was performed to determine the difference in progression-free survival (PFS) between the two groups with the prediction label generated by the combined model. The radiomic model based on the combination of precontrast and postcontrast CT radiomic features and the clinical model produced an AUC of 0.92±0.04 and 0.89±0.03, respectively. By integrating radiomic and clinical features together, the combined model had the best performance with an AUC of 0.94±0.02. The survival analysis showed that the two groups had significantly different PFS times (p<0.0001). The baseline multidimensional data including CT radiomic and multiple clinical features were valuable in predicting the efficacy of ICIs monotherapy in patients with advanced NSCLC.

Risk stratification and pathway analysis based on graph neural network and interpretable algorithm.

BACKGROUND: Pathway-based analysis of transcriptomic data has shown greater stability and better performance than traditional gene-based analysis. Until now, some pathway-based deep learning models have been developed for bioinformatic analysis, but these models have not fully considered the topological features of pathways, which limits the performance of the final prediction result. RESULTS: To address this issue, we propose a novel model, called PathGNN, which constructs a Graph Neural Networks (GNNs) model that can capture topological features of pathways. As a case, PathGNN was applied to predict long-term survival of four types of cancer and achieved promising predictive performance when compared to other common methods. Furthermore, the adoption of an interpretation algorithm enabled the identification of plausible pathways associated with survival. CONCLUSION: PathGNN demonstrates that GNN can be effectively applied to build a pathway-based model, resulting in promising predictive power.

Circulation, genomic characteristics, and evolutionary dynamics of class I Newcastle disease virus in China.

Newcastle disease caused by Newcastle disease virus (NDV) is one of the most serious threats to chickens and has two clinical forms, typical and atypical, caused by velogenic and lentogenic strains, respectively. To control the epidemic, many vaccines against velogenic class II NDVs have been introduced worldwide, but this has led to accelerated mutation of class II viruses under immune pressure and, on the other hand, to non-vaccine targeting class I NDVs becoming the dominant population in poultry. In this context, this study provided the first large-scale genomic epidemiological and quasispecies dynamic analysis of class I NDVs in China, and found that class I viruses that first appeared in East and South China have spread to central China and become the dominant class with an average evolutionary rate of 1.797 × 10-3. In addition, single nucleotide polymorphism and intra-host single nucleotide variation analyses show that HN and P genes have high mutation rates and may act as front-runners for NDV to expand their host range and enhance their virulence. This study also found that the class I NDV population has accumulated a number of mutations under positive selection and that six isolates with shortened C-terminal extensions of the HN protein are evolving toward increased virulence. These results not only enrich the research resources but also help us to better understand the dynamic evolution and mutational trends of NDV at the genomic level, which is crucial for monitoring, early warning, and controlling the outbreak of Newcastle disease.

Ecology of avian influenza viruses in migratory birds wintering within the Yangtze River wetlands.

Migratory birds are considered natural reservoirs of avian influenza A viruses (AIVs). To further our viral ecology knowledge and understand the subsequent risk posed by wild birds, we conducted a 4-year surveillance study of AIVs in the bird wintering wetlands of the Yangtze River, China. We collected over 8000 samples and isolated 122 AIV strains. Analyses were then carried out with 108 novel sequenced genomes and data were deposited in GISAID and other public databases. The results showed that the Yangtze River wintering wetlands functioned as a mixing ground, where various subtypes of AIVs were detected harboring a high diversity of nucleotide sequences; moreover, a portion of AIV gene segments were persistent inter-seasonally. Phylogenetic incongruence presented complex reassortment events and distinct patterns among various subtypes. In addition, we observed that viral gene segments in wintering wetlands were closely related to known North American isolates, indicating that intercontinental gene flow occurred. Notably, highly pathogenic H5 and low pathogenic H9 viruses, which usually circulate in poultry, were found to have crossed the poultry/wild bird interface, with the viruses introduced to wintering birds. Overall, this study represented the largest AIV surveillance effort of wild birds within the Yangtze River wintering wetlands. Surveillance data highlighted the important role of wintering wild birds in the ecology of AIVs and may enable future early warnings of novel AIV emergence.

Transcription profile of human endogenous retroviruses in response to dengue virus serotype 2 infection.

Human endogenous retroviruses (HERVs), the remains of retroviruses infection in our ancestors' germline cell over millions of years, take up about 8% of the human genome in total. HERV transcription has been detected in various cancers and diseases. However, the interaction between HERV expression and viral infection has not been fully elucidated. Here, we provided the first transcriptional profile of HERVs in dengue virus serotype 2 (DENV-2) infected A549 cells by using high-throughput RNA sequencing. The results showed that a number of HERVs and human genes were significantly differentially expressed in response to DENV-2 infection. Further bioinformatic analyses indicated a correlation between HERVs and human genes. In particular, the genes near the HERVs activated by dengue infection were dominantly enriched in the antiviral immune response. Taken together, our findings suggest that activated HERVs may be involved in the cellular immune response to viral infection by coexpressing with nearby host genes.

Circulation, Evolution and Transmission of H5N8 virus, 2016-2018.

OBJECTIVES: A second wave of highly pathogenic avian influenza A virus (HPAIV) H5N8 clade 2.3.4.4 has spread globally, causing outbreaks among wild birds and domestic poultry since autumn 2016. The circulation and evolutionary dynamics of the virus remain largely unknown. METHODS: We performed surveillance for H5N8 in Qinghai Lake in China since the emergence of the virus (from 2016 to 2018). By analyzing recovered viruses in Qinghai Lake and all related viruses worldwide (449 strains), we identified the genotypes, estimated their genesis and reassortment, and evaluated their global distribution and transmission. RESULTS: Through surveillance of wild migratory birds around Qinghai Lake between 2016 and 2018, we revealed that the H5N8 was introduced into Qinghai Lake bird populations (QH-H5N8), with distinct gene constellations in 2016 and 2017. A global analysis of QH-H5N8-related viruses showed that avian influenza viruses with low pathogenicity in wild birds contributed to the high diversity of genotypes; the major reassortment events possibly occurred during the 2016 breeding season and the following winters. CONCLUSIONS: Continued circulation of QH-H5N8-related viruses among wild birds has resulted in the global distribution of high genotypic diversity. Thus, these viruses pose an ongoing threat to wild and domestic bird populations and warrant continuous surveillance.

Network pharmacology based investigation into the effect and mechanism of Modified Sijunzi Decoction against the subtypes of chronic atrophic gastritis.

Chronic atrophic gastritis (CAG) is a common digestive disease without specific treatment. According to syndrome differentiation, traditional Chinese medicine (TCM) classified it into different syndromes and has achieved significant therapeutic effects. In this study, immune repertoire sequencing techniques combined with symptom scores, electronic gastroscopy as well as pathologic changes were used to evaluate the effect and the underlying mechanism of Modified Sijunzi Decoction (MSD) in treating CAG. The results showed that MSD could relieve CAG symptoms, improve pathologic changes in CAG with fatigue and tiredness symptom, but with no help in CAG with reversal heat symptom. Moreover, MSD could regulate immune disorders in CAG with fatigue and tiredness symptom, and 7 TCR biomarkers were explored in CAG patients with immune disorders. All these results indicated that MSD is effective in treating CAG patients with fatigue and tiredness symptom by tonifying the spleen qi, suggesting that CAG treatment based on syndrome differentiation is reasonable.

Phylogeography, Transmission, and Viral Proteins of Nipah Virus.

Nipah virus (NiV), a zoonotic paramyxovirus belonging to the genus Henipavirus, is classified as a Biosafety Level-4 pathogen based on its high pathogenicity in humans and the lack of available vaccines or therapeutics. Since its initial emergence in 1998 in Malaysia, this virus has become a great threat to domestic animals and humans. Sporadic outbreaks and person-to-person transmission over the past two decades have resulted in hundreds of human fatalities. Epidemiological surveys have shown that NiV is distributed in Asia, Africa, and the South Pacific Ocean, and is transmitted by its natural reservoir, Pteropid bats. Numerous efforts have been made to analyze viral protein function and structure to develop feasible strategies for drug design. Increasing surveillance and preventative measures for the viral infectious disease are urgently needed.

Evaluation of cell death pathways initiated by antitumor drugs melatonin and valproic acid in bladder cancer cells.

Effective drug combinations have the potential to strengthen therapeutic efficacy and combat drug resistance. Both melatonin and valproic acid (VPA) exhibit antitumor activities in various cancer cells. The aim of this study was to evaluate the cell death pathways initiated by anticancer combinatorial effects of melatonin and VPA in bladder cancer cells. The results demonstrated that the combination of melatonin and VPA leads to significant synergistic growth inhibition of UC3 bladder cancer cells. Gene expression studies revealed that cotreatment with melatonin and VPA triggered the up-regulation of certain genes related to apoptosis (TNFRSF10A and TNFRSF10B), autophagy (BECN, ATG3 and ATG5) and necrosis (MLKL, PARP-1 and RIPK1). The combinatorial treatment increased the expression of endoplasmic reticulum (ER)-stress-related genes ATF6, IRE1, EDEM1 and ERdj4. Cotreatment with melatonin and VPA enhanced the expression of E-cadherin, and decreased the expression of N-cadherin, Fibronectin, Snail and Slug. Furthermore, the Wnt pathway and Raf/MEK/ERK pathway were activated by combinatorial treatment. However, the effects on the expression of certain genes were not further enhanced in cells following combinatorial treatment in comparison to individual treatment of melatonin or VPA. In summary, these findings provided evidence that cotreatment with melatonin and VPA exerted increased cytotoxicity by regulating cell death pathways in UC3 bladder cancer cells, but the clinical significance of combinatorial treatment still needs to be further exploited.